Senior AI Software Engineer – Agentic AI / Python
Job at a Glance
Title: Senior AI Software Engineer – Agentic AI / Python
Location: Orlando, FL (onsite 4 days per week)
Contract: W2 only, 12 month contract with potential for extension or conversion to full time with either the client or CEI
Pay: $75-$80/hour + optional medical, dental, vision, 401(k) match
Overview
We are seeking a Senior AI Software Engineer to help advance and productionize a sophisticated agentic AI platform. This role will focus on taking an existing, highly functional AI agent prototype and evolving it into a scalable, observable, and production-ready solution. You will work in a highly iterative environment where experimentation, rapid feedback, and continuous improvement are expected.
Key Responsibilities
- Design, build, and enhance production-grade Python services supporting agentic AI applications.
- Develop and refine multi-agent LLM workflows using frameworks such as Google ADK, LangGraph, A2A, or comparable technologies.
- Implement agent orchestration, tool use, guardrails, structured outputs, and workflow logic.
- Help transition advanced AI prototypes into scalable, reliable production services.
- Establish and improve logging, monitoring, tracing, observability, and operational visibility for AI agents.
- Develop evaluation strategies for LLM and agent performance, including quality, safety, accuracy, and behavioral metrics.
- Support A/B testing and experimentation to continuously improve agent performance.
- Build and maintain integrations with services and APIs consumed by AI agents.
- Work extensively with GCP and Vertex AI for AI services, model serving, retrieval, search, and related platform capabilities.
- Apply prompt engineering techniques to improve agent behavior and response quality.
- Design reliable structured outputs and schemas using tools such as Pydantic.
- Containerize services and support automated build, test, deployment, and CI/CD processes.
- Collaborate with product and engineering teams in a fast-moving Agile environment.
- Troubleshoot production issues across AI agents, backend services, integrations, and supporting infrastructure.
- Continuously iterate on architectures, prompts, tools, and workflows as the platform evolves.
Required Skills
- Strong professional experience developing production-grade Python applications and backend services.
- Advanced knowledge of asynchronous Python, including async/await, concurrency, and asynchronous service architectures.
- Hands-on experience with FastAPI, ASGI, or comparable Python API frameworks.
- Proven experience developing agentic or multi-agent LLM applications.
- Experience with Google ADK, LangGraph, A2A, or similar agent orchestration frameworks.
- Strong understanding of agent tool use, orchestration, workflows, guardrails, and state management.
- Hands-on experience with LLMOps, AI evaluation, or agent evaluation.
- Experience with tools or platforms such as Phoenix/Arize, Vertex AI Evaluation, OpenTelemetry, or comparable observability and evaluation technologies.
- Strong experience with Google Cloud Platform and Vertex AI.
- Experience building production services with containers and modern CI/CD practices.
- Experience with observability, logging, monitoring, and tracing within distributed production systems.
- Strong prompt engineering skills and experience refining LLM behavior through experimentation and evaluation.
- Experience designing structured LLM outputs and schemas using Pydantic or similar technologies.
- Strong software engineering fundamentals and the ability to work effectively in a rapidly evolving, highly iterative environment.
Required Education
- Bachelor’s degree in Computer Science, Software Engineering, Information Technology, Engineering, or a related technical field required.
Preferred Skills
- Experience with Retrieval-Augmented Generation (RAG), embeddings, and vector search.
- Experience supporting large-scale MySQL or other relational database environments.
- Knowledge of enterprise authentication and authorization, including OAuth2 and scopes.
- Experience with MLOps platforms, experimentation, and model or prompt tracking.
- Experience mentoring engineers or contributing to architecture and technical direction.
- Java development experience, particularly Java Reactor / reactive programming.
- Experience integrating AI applications with Java-based or reactive backend services.
- Experience taking Generative AI or agentic AI solutions from prototype through production.
Why Should I Apply?
This role offers the opportunity to productionize an advanced agentic AI prototype into a scalable, observable platform while working in a highly iterative engineering environment.
About CEI:
As a trusted technology partner, CEI delivers solutions that help our customers transform their business and achieve meaningful results. From strategy and custom application development through application management - our technology and digital experience services are tailored to meet each unique need of our customers. Our staffing solutions bring specialized skills to complement our customers'' workforce and project requirements.
#ZR #INDGEN